Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state that the title is discarded after the call, which is a useful data-retention trait. However, it does not disclose whether the tool makes a network request, how the existence result is returned, or any error/rate-limit behavior. The single behavioral note is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, containing only two sentences with no filler or repetitive information. The primary purpose is front-loaded, and every word serves a function. This is an efficient and well-structured brief description, even though it omits critical details covered in other dimensions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is inadequate for the tool's complexity. With no output schema, no annotations, and a seven-parameter input schema, the description fails to explain which parameter holds the Wikipedia title or what the result of the existence check looks like. An agent cannot safely invoke this tool based on the provided information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema lists seven string parameters (ref, url, city, feed, host, json, path) whose descriptions all revolve around shape checks and discarding, with none mentioning 'title'. The tool description says 'Check whether a Wikipedia title exists' but never maps the title to any schema parameter. This leaves the agent unable to determine which field to populate, a critical gap. The high schema coverage is irrelevant because the descriptions are generic and do not align with the tool's purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Check whether a Wikipedia title exists') with a specific resource (Wikipedia title), distinguishing it from sibling tools like browser-url-ok or domain-shape which target different resources. The verb 'check' and the object 'Wikipedia title' are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or conditions. An agent cannot determine whether to choose wiki-title-ok over siblings such as web-fetch or normalize-url. There is no stated context or exclusion that would help route the call.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.